Presentation is loading. Please wait.

Presentation is loading. Please wait.

1 | Program Name or Ancillary Texteere.energy.gov BTO Program Peer Review Autotune Building Energy Models Joshua New Oak Ridge National Laboratory

Similar presentations


Presentation on theme: "1 | Program Name or Ancillary Texteere.energy.gov BTO Program Peer Review Autotune Building Energy Models Joshua New Oak Ridge National Laboratory"— Presentation transcript:

1 1 | Program Name or Ancillary Texteere.energy.gov BTO Program Peer Review Autotune Building Energy Models Joshua New Oak Ridge National Laboratory April 2, 2013

2 2 | Building Technologies Officeeere.energy.gov Purpose & Objectives Problem Statement: All (building energy) models are wrong, but some are useful –22%-97% different from utility data for 3,349 buildings More accurate models are more useful –Error from inputs and algorithms for practical reasons –Useful for cost-effective energy efficiency (EE) at speed and scale Calibration is required to be (legally) useful –ASHRAE G14 (NMBE<5/10% and CV(RMSE)<15/30% monthly/hourly) Manual calibration is risk/cost-prohibitive –Development costs 10-45% of federal ESPC projects <$1M Need robust and scalable automated calibration for market –Adjusts parameters in a physically realistic manner –Scales to any available data and model (audit)

3 3 | Building Technologies Officeeere.energy.gov Purpose & Objectives Impact of Project: Reduces transaction cost of developing and selling EE improvement projects in existing buildings Enables the ESCO business model to reach smaller buildings and projects Enables speed and scale deployment approaches based on every building in served area having a continuously maintained calibrated model (audit) Enables tracked actual performance of implemented EE measures to improve model (audit) over time Project endpoint is an automated calibration package that users of simulation tools can deploy as they choose.

4 4 | Building Technologies Officeeere.energy.gov Purpose & Objectives Project Focus: Objective: Develop a generalized, automated model (audit) tuning methodology that enables the model (audit) to reproduce measured data as best it can, by selecting best-match input parameters in a systematic, automated, and repeatable fashion. BTO Goals: supports the BTO overarching goal of reducing building energy use 50% by 2030 BTO strategic programs: Autotune is listed as a key service within the BTO Strategic BEM Portfolio

5 5 | Building Technologies Officeeere.energy.gov Approach Approach: Multi-objective optimization algorithms to minimize error between simulation output and measured data by intelligently adjusting building model inputs Sensitivity analysis and uncertainty quantification to determine importance of individual parameters Suite of machine learning algorithms to generate calibration functions based on building dynamics Quantify trade-off between tuning accuracy and amount of data available Creation of intuitive Autotune application on users PC or website with database, software tools, and accelerated tuning agents in the background

6 6 | Building Technologies Officeeere.energy.gov Approach Approach: Demonstrations of end-to-end Autotune prototype on: –ORNLs fleet of research houses and light commercial test buildings (flexible research platforms) –Weatherization and audit buildings in the wild Key Issues: How well does it reproduce measured data? How long does it take? How well does this represent the actual building?

7 7 | Building Technologies Officeeere.energy.gov Approach Distinctive Characteristics: Method scalable to available data Methods employed are model (audit) agnostic Can be used to speed up model (audit) runtime Capabilities in place for big data mining Interactive dashboard for Autotune progress Repeatable tuning results

8 8 | Building Technologies Officeeere.energy.gov Accomplishments and Progress Accomplishments: End-to-end Windows desktop prototype created Overnight tuning of envelope-only parameters, 61% as accurate as 4 man-months of effort Autotune 156 EnergyPlus inputs in 3 hours on desktop was within 30 ¢ /day (actual use $4.97/day) Autotune for National Energy Audit Tool (NEAT) –15 inputs (±30%), reduced error 48%, 20mins on netbook –Experts would have tuned same way; 9,154 buildings Trinity test shows G14 compliance and realistic tuning –Outputs: CV(RMSE)<2.5%, NMBE<1% both hourly and monthly –Inputs: For 60% range, Autotune is close to real value (within 8% when tuning to hourly data, 15% when tuning to monthly data)

9 9 | Building Technologies Officeeere.energy.gov Accomplishments and Progress Accomplishments: Titan scalability – 65k cores, 262,144 EnergyPlus (9TB), 44mins MLSuite allows easy use of software on supercomputers Tableau and Google Vis API interactive visualization and comparison of all Autotune experiments Progress on Goals: Tuning accuracy satisfies ASHRAE Guideline 14 Less than 3 hours on standard computer Physically realistic results

10 10 | Building Technologies Officeeere.energy.gov Accomplishments and Progress Awards/Recognition: 2+ million core-hours, 4 competitive awards (free cost share) Extreme Science and Engineering Discovery Environment (XSEDE) –Nautilus 30k core-hours (CY11), 200k (CY12), 500k (CY13) Oak Ridge Leadership Computing Facility (OLCF) –Jaguar 500k core-hours (CY12), Titan 500k (CY13), Frost 200k (CY13), Lens/EVEREST (CY12&13)

11 11 | Building Technologies Officeeere.energy.gov Project Plan & Schedule Project initiation date: Oct (FY12) Project planned completion date: Sept (FY14) Schedule and Milestones: FY12 – 10 DOE deliverables on time and budget FY13 – 7 of 14 DOE deliverables so far, all on time and budget

12 12 | Building Technologies Officeeere.energy.gov Project Budget Cost to Date: –FY12: fully costed –FY13: $119k (45%) Funding Sources: Budget History FY2012FY2013 DOECost-shareDOECost-share $650k$980k$264k$1,225k

13 13 | Building Technologies Officeeere.energy.gov Project Integration, Collaboration & Market Impact Partners, Subcontractors, and Collaborators: Technology Transfer, Deployment, Market Impact: Autotune Invention Disclosure filed 5 software systems to copyright and release Plan to deploy Autotune in FY13 Karpay Associates Jacksonville State University The University of Tennessee

14 14 | Building Technologies Officeeere.energy.gov Project Integration, Collaboration & Market Impact Communications (selected): 1 PhD Dissertation, 2 journals, 5 conference, 6 submitted soon, 5 internal reports (250+ pages) Published: New, Joshua R., Sanyal, Jibonananda, Bhandari, Mahabir S., Shrestha, Som S. (2012). "Autotune EnergyPlus Building Energy Models." In Proceedings of the 5th National SimBuild of IBPSA-USA, International Building Performance Simulation Association (IBPSA), Aug. 1-3, [PDF pre-print]PDF pre-print Sanyal, Jibonananda, Al-Wadei, Yusof H., Bhandari, Mahabir S., Shrestha, Som S., Karpay, Buzz, Garret, Aaron L., Edwards, Richard E., Parker, Lynne E., and New, Joshua R. (2012). "Poster: Building Energy Model Calibration using EnergyPlus, Machine Learning, and Supercomputing." In Proceedings of the 5th National SimBuild of IBPSA-USA, International Building Performance Simulation Association, Aug. 1-3, [PDF]PDF Accepted: Garrett, Aaron, New, Joshua R., and Chandler, Theodore. Evolutionary Tuning of Building Models to Monthly Electrical Consumption. ASHRAE Conference in Denver, CO, June 22-26, Sanyal, Jibonananda and New, Joshua R. Simulation and Big Data Challenges in Tuning Building Energy Models. IEEE Workshop on Modeling and Simulation of Cyber-Physical Energy Systems, May Planned/submitted: Edwards, Richard E., New, Joshua R., and Parker, Lynne E. Constructing Large Scale EnergyPlus Surrogates from Big Data. To be submitted to Energy & Buildings Journal, Garrett, Aaron and New, Joshua R. Scalable Evolutionary Tuning of Building Models to Multiple Channels of Sub-Hourly Data. To be submitted to ASHRAE, New York City, NY, Jan , Internal: Edwards, Richard E., and Parker, Lynne E. (2013). MLSuite - FY2012 Final Report. 68 pages Garrett, Aaron and New, Joshua R. (2012). An Evolutionary Approach to Parameter Tuning of Building Models. 68 pages Edwards, Richard E., New, Joshua R., and Parker, Lynne E. (2012) Approximate l-fold cross-validation with Least Squares SVM and Kernel Ridge Regression. 9 pages

15 15 | Building Technologies Officeeere.energy.gov Next Steps and Future Plans Next Steps and Future Plans: BTO – finish Autotune project as detailed BTO – deploy in residential and commercial building integration program elements Weatherization – Autotune NEAT comparison of human vs. computer calibration Federal Energy Management Program – ESPC ENABLE program


Download ppt "1 | Program Name or Ancillary Texteere.energy.gov BTO Program Peer Review Autotune Building Energy Models Joshua New Oak Ridge National Laboratory"

Similar presentations


Ads by Google